REVIEW 1 cited by
Towards Better Data Augmentation using Wasserstein Distance in Variational Auto-encoder
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
VAE, or variational auto-encoder, compresses data into latent attributes, and generates new data of different varieties. VAE based on KL divergence has been considered as an effective technique for data augmentation. In this paper, we propose the use of Wasserstein distance as a measure of distributional similarity for the latent attributes, and show its superior theoretical lower bound (ELBO) compared with that of KL divergence under mild conditions. Using multiple experiments, we demonstrate that the new loss function exhibits better convergence property and generates artificial images that could better aid the image classification tasks.
Forward citations
Cited by 1 Pith paper
-
From Points to Spheres: A Geometric Reinterpretation of Variational Autoencoders
The paper claims that KL-induced compactness, not stochasticity, is the key to VAE generative capability, supported by new latent-space uniformity metrics and codebook regularizer experiments.
Discussion (0). Sign in to comment.